© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 62108
    Prev
    Next
    INDEX
    Explanations

    key action verbs that convey significance or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     themselves
    -0.07
    ocache
    -0.07
     their
    -0.06
    ion
    -0.06
     Bol
    -0.06
     Gad
    -0.06
    hn
    -0.06
    etto
    -0.06
    cn
    -0.06
    olk
    -0.06
    POSITIVE LOGITS
    /***/
    0.08
    edn
    0.08
    ĵåIJį
    0.08
    tape
    0.08
    LEC
    0.08
    iner
    0.07
    paralle
    0.07
    èĥİ
    0.07
    radan
    0.07
    CustomLabel
    0.07
    Activations Density 0.120%

    No Known Activations